About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
Algorithms Development in Materials Science and Engineering
|
| Presentation Title |
A Mechanistic and Data Hybrid Model for Predicting Si and Mn Contents at LF Refining Endpoint |
| Author(s) |
Zhengjiang Yang, Mingmei Zhu, Xianwu Zhang, Chenghong Li, Xianhong Qin |
| On-Site Speaker (Planned) |
Zhengjiang Yang |
| Abstract Scope |
Accurate prediction of molten steel composition at the LF refining endpoint is the key to improve the quality of high-end steel products. In the paper, a mechanistic and data hybrid model was proposed for predicting Si and Mn contents at LF refining endpoint. First, the mechanistic models were constructed based on metallurgical principles to clarify the key influence parameters. Then, the genetic algorithm (GA) was introduced to optimize the hyperparameters of the backpropagation neural network (BPNN), and a data-driven model was used to solve the key parameters of the mechanistic model, achieving the integration of mechanism constraints and data optimization in modeling. The production big data in a plant was used as samples to validate the model. The results showed that the hit rates of Si and Mn contents in the range of ±0.005% were 93.2% and 91.2%, respectively, which significantly improved the prediction accuracy. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Machine Learning, |